Fully complex extreme learning machine

被引：253

作者：

Li, MB ^{[1
]}

Huang, GB ^{[1
]}

Saratchandran, P ^{[1
]}

Sundararajan, N ^{[1
]}

机构：

[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore

来源：

NEUROCOMPUTING | 2005年 / 68卷 / 1-4期

关键词：

feedforward neural networks; complex QAM equalization; complex extreme learning machine; complex activation function; CMRAN; CRBF; CBP;

D O I：

10.1016/j.neucom.2005.03.002

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recently, a new learning algorithm for the feedforward neural network named the extreme learning machine (ELM) which can give better performance than traditional tuning-based learning methods for feedforward neural networks in terms of generalization and learning speed has been proposed by Huang et al. In this paper, we first extend the ELM algorithm from the real domain to the complex domain, and then apply the fully complex extreme learning machine (C-ELM) for nonlinear channel equalization applications. The simulation results show that the ELM equalizer significantly outperforms other neural network equalizers such as the complex minimal resource allocation network (CMRAN), complex radial basis function (CRBF) network and complex backpropagation (CBP) equalizers. C-ELM achieves much lower symbol error rate (SER) and has faster learning speed. (c) 2005 Elsevier B.V. All rights reserved.

引用

页码：306 / 314

页数：9